commit 87591094b2ee09d24fba64ba35c1b51bebdf5e06 Author: ModelHub XC Date: Fri Jul 10 18:58:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Kuvera-8B-v0.1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fb3af15 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Kuvera-8B-v0.1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Kuvera-8B-v0.1.0.IQ4_XS.gguf b/Kuvera-8B-v0.1.0.IQ4_XS.gguf new file mode 100644 index 0000000..8bb5223 --- /dev/null +++ b/Kuvera-8B-v0.1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67502a845d4599b0ba62795f885888b0838c8e925bd5d434140a6015bea31a7c +size 4593297440 diff --git a/Kuvera-8B-v0.1.0.Q2_K.gguf b/Kuvera-8B-v0.1.0.Q2_K.gguf new file mode 100644 index 0000000..5142043 --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3443dceae7370a7ab3d039ac3ff14721a445cbac873241c79e86edcbd0bfbf45 +size 3281733664 diff --git a/Kuvera-8B-v0.1.0.Q3_K_L.gguf b/Kuvera-8B-v0.1.0.Q3_K_L.gguf new file mode 100644 index 0000000..bb84963 --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f18c5e3f2a49c7b3b624479fc332c9c7c6665031ec2bd165562277cf484b901 +size 4431394848 diff --git a/Kuvera-8B-v0.1.0.Q3_K_M.gguf b/Kuvera-8B-v0.1.0.Q3_K_M.gguf new file mode 100644 index 0000000..c7cee2e --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f7b3cc2925ad1f946553698666c8e8de7cf02b75721f788cbafc7b5d33a3d5c +size 4124162080 diff --git a/Kuvera-8B-v0.1.0.Q3_K_S.gguf b/Kuvera-8B-v0.1.0.Q3_K_S.gguf new file mode 100644 index 0000000..e34de31 --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c445a8207d920916834a231491e9f1b879a6e34f3da8fbb9bcd441a5ce2ae80 +size 3769612320 diff --git a/Kuvera-8B-v0.1.0.Q4_K_M.gguf b/Kuvera-8B-v0.1.0.Q4_K_M.gguf new file mode 100644 index 0000000..3e9e85e --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d1703f03ec85e37bccd3ba30d8e314fbc79280b65e4ace8acb56ec76d09567 +size 5027784736 diff --git a/Kuvera-8B-v0.1.0.Q4_K_S.gguf b/Kuvera-8B-v0.1.0.Q4_K_S.gguf new file mode 100644 index 0000000..cff95ff --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b044cc60a4a9317fc51095357551423e6e8af90fddbf339ed1dc638ac344c7 +size 4802013216 diff --git a/Kuvera-8B-v0.1.0.Q5_K_M.gguf b/Kuvera-8B-v0.1.0.Q5_K_M.gguf new file mode 100644 index 0000000..123d1cb --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6999b337332a665aa79c670237d653e10527e0b99083a0c543c310d3c33f01c +size 5851113504 diff --git a/Kuvera-8B-v0.1.0.Q5_K_S.gguf b/Kuvera-8B-v0.1.0.Q5_K_S.gguf new file mode 100644 index 0000000..1944d48 --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a57cd21d3b114ca3ca3fe03a70b2527156e315b7f65df4f528aefd6e737dc61e +size 5720762400 diff --git a/Kuvera-8B-v0.1.0.Q6_K.gguf b/Kuvera-8B-v0.1.0.Q6_K.gguf new file mode 100644 index 0000000..0892e31 --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30fc771eed924676608f8279a6abf9144de9c0442b2afc6f4a150965363457be +size 6725900320 diff --git a/Kuvera-8B-v0.1.0.Q8_0.gguf b/Kuvera-8B-v0.1.0.Q8_0.gguf new file mode 100644 index 0000000..224bad1 --- /dev/null +++ b/Kuvera-8B-v0.1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af7d4a9ebac1c5572da26f2bb17a6350d940b110bc104bfea85b2bba047b1d2c +size 8709519392 diff --git a/Kuvera-8B-v0.1.0.f16.gguf b/Kuvera-8B-v0.1.0.f16.gguf new file mode 100644 index 0000000..8ae346b --- /dev/null +++ b/Kuvera-8B-v0.1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c22022764837087346bc3ddc5202aa98aa405c82748e040a133f18ae7e9aa63 +size 16388044832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0c7b20a --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: Akhil-Theerthala/Kuvera-8B-v0.1.0 +datasets: +- Akhil-Theerthala/Personal-Finance-Queries +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- finance +- personal_finance +- Qwen3 +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/Akhil-Theerthala/Kuvera-8B-v0.1.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Kuvera-8B-v0.1.0-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Kuvera-8B-v0.1.0-GGUF/resolve/main/Kuvera-8B-v0.1.0.f16.gguf) | f16 | 16.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +